Incidental Supervision: Moving beyond Supervised Learning

Abstract

Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on it. However, learning models for these tasks is difficult partly because generating the necessary supervision signals for it is costly and does not scale. This paper describes several learning paradigms that are designed to alleviate the supervision bottleneck. It will illustrate their benefit in the context of multiple problems, all pertaining to inducing various levels of semantic representations from text.

6 pages, 1 figure. Appeared in AAAI-17

Cited by in corpus (10)

• Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text
• Fidelity-Weighted Learning
• Cross-lingual Entity Alignment with Incidental Supervision
• Named Entity Recognition with Partially Annotated Training Data
• Zero-Shot Open Entity Typing as Type-Compatible Grounding
• Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
• QuASE: Question-Answer Driven Sentence Encoding
• Learning Constraints and Descriptive Segmentation for Subevent Detection
• Self-supervised self-supervision by combining deep learning and probabilistic logic
• Partial Or Complete, That's The Question